Information extraction is the prerequisite of remote sensing image segmentation, which is the key procedure of image analysis. In this paper hard C-means and fuzzy C-means is adopted for segmentation in remote sensing image to realize our road extraction. Firstly, we proposed k-means for image segmentation using non-supervised clustering, and we can achieve our aim finally. Meanwhile, SVM combined with Fuzzy C means was proposed and this model was implemented in remote sensing image segmentation to extract the road net. Finally the comparison with two proposed algorithm was carried out, and after experiment, SVM plus FCM model is much more accurate than k-means.
A Spatial Guided Self-supervised Clustering Network for Medical Image Segmentation